
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.preprocessing import StandardScaler
from sklearn.decomposition import PCA
from sklearn.cluster import KMeans
from sklearn.metrics import silhouette_score
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.tree import DecisionTreeRegressor
from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import mean_squared_error, r2_score, mean_absolute_error


df = pd.read_csv('MS4S16_Resit_Dataset.csv')
df


numerical_cols = df.select_dtypes(include=[np.number]).columns.tolist()
numerical_cols

['Solubility',
 'SD',
 'Ocurrences',
 'MolWt',
 'MolLogP',
 'MolMR',
 'HeavyAtomCount',
 'NumHAcceptors',
 'NumHDonors',
 'NumHeteroatoms',
 'NumRotatableBonds',
 'NumValenceElectrons',
 'NumAromaticRings',
 'NumSaturatedRings',
 'NumAliphaticRings',
 'RingCount',
 'TPSA',
 'LabuteASA',
 'BalabanJ',
 'BertzCT']


categorical_cols = df.select_dtypes(include=['object', 'category']).columns.tolist()
categorical_cols

['ID', 'Name', 'InChI', 'InChIKey', 'SMILES', 'Group']


df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 9982 entries, 0 to 9981
Data columns (total 26 columns):
 #   Column               Non-Null Count  Dtype  
---  ------               --------------  -----  
 0   ID                   9982 non-null   object 
 1   Name                 9982 non-null   object 
 2   InChI                9982 non-null   object 
 3   InChIKey             9982 non-null   object 
 4   SMILES               9982 non-null   object 
 5   Solubility           9982 non-null   float64
 6   SD                   9982 non-null   float64
 7   Ocurrences           9982 non-null   int64  
 8   Group                9982 non-null   object 
 9   MolWt                9982 non-null   float64
 10  MolLogP              9982 non-null   float64
 11  MolMR                9982 non-null   float64
 12  HeavyAtomCount       9982 non-null   float64
 13  NumHAcceptors        9982 non-null   float64
 14  NumHDonors           9982 non-null   float64
 15  NumHeteroatoms       9982 non-null   float64
 16  NumRotatableBonds    9982 non-null   float64
 17  NumValenceElectrons  9982 non-null   float64
 18  NumAromaticRings     9982 non-null   float64
 19  NumSaturatedRings    9982 non-null   float64
 20  NumAliphaticRings    9982 non-null   float64
 21  RingCount            9982 non-null   float64
 22  TPSA                 9982 non-null   float64
 23  LabuteASA            9982 non-null   float64
 24  BalabanJ             9982 non-null   float64
 25  BertzCT              9982 non-null   float64
dtypes: float64(19), int64(1), object(6)
memory usage: 2.0+ MB


df.describe()


df[numerical_cols].hist(figsize=(12, 10))
plt.show()


def remove_outliers(df, col):
    q1 = df[col].quantile(0.25)
    q3 = df[col].quantile(0.75)
    iqr = q3 - q1
    lower_bound = q1 - 1.5 * iqr
    upper_bound = q3 + 1.5 * iqr
    return df[(df[col] >= lower_bound) & (df[col] <= upper_bound)]

def annotate_boxplot(ax, data, col):
    min_val = data.min()
    q1 = data.quantile(0.25)
    median = data.median()
    q3 = data.quantile(0.75)
    max_val = data.max()
    
    textstr = f'Min: {min_val:.2f}\nQ1: {q1:.2f}\nMedian: {median:.2f}\nQ3: {q3:.2f}\nMax: {max_val:.2f}'
    props = dict(boxstyle='round,pad=0.3', edgecolor='black', facecolor='none')
    ax.text(0.05, -0.1, textstr, transform=ax.transAxes, fontsize=10,
            verticalalignment='top', bbox=props)

numerical_cols = df.select_dtypes(include='number').columns

for col in numerical_cols:
    plt.figure(figsize=(20, 5))
    ax = sns.boxplot(x=df[col])
    annotate_boxplot(ax, df[col], col)
    plt.title(f'Boxplot of {col}')
    plt.show()


plt.figure(figsize = (20,8))
sns.histplot(df['NumAromaticRings'], kde=True)
plt.title('NumAromaticRings Distribution')
plt.ylabel("Frequency")
plt.show()


plt.figure(figsize = (20,8))
sns.histplot(df['NumAromaticRings'], kde=True)
plt.title('NumAromaticRings Distribution')
plt.ylabel("Frequency")
plt.show()


plt.figure(figsize = (20,8))
sns.histplot(df['SD'], kde=True)
plt.title('SD Distribution')
plt.ylabel("Frequency")
plt.show()


plt.figure(figsize = (20,8))
sns.histplot(df['Ocurrences'], kde=True)
plt.title('Ocurrences Distribution')
plt.ylabel("Frequency")
plt.show()


df.query('Ocurrences > 6')


plt.figure(figsize = (20,8))
sns.histplot(df['RingCount'], kde=True)
plt.title('RingCount Distribution')
plt.ylabel("Frequency")
plt.show()


plt.figure(figsize = (20,9))
sns.histplot(df['NumAliphaticRings'], kde=True)
plt.title('NumAliphaticRings Distribution')
plt.ylabel("Frequency")
plt.show()


plt.figure(figsize = (20,9))
sns.histplot(df['NumSaturatedRings'], kde=True)
plt.title('NumSaturatedRings Distribution')
plt.ylabel("Frequency")
plt.show()


plt.figure(figsize=(10, 6))
ax = sns.violinplot(x='Group', y='Solubility', data=df)
plt.title('Violin plot of Solubility by Group')
plt.xlabel('Group')
plt.ylabel('Solubility')
plt.xticks(rotation=45)

# Calculate and annotate median, quartiles, min, and max
groups = df['Group'].unique()
for group in groups:
    data = df[df['Group'] == group]['Solubility']
    median = data.median()
    q1 = data.quantile(0.25)
    q3 = data.quantile(0.75)
    min_val = data.min()
    max_val = data.max()
    
    pos = groups.tolist().index(group)
    ax.annotate(f'Min: {min_val:.2f}', xy=(pos, min_val), xytext=(pos, min_val - 0.5),
                arrowprops=dict(facecolor='orange', arrowstyle='->'), ha='center')
    ax.annotate(f'Q1: {q1:.2f}', xy=(pos, q1), xytext=(pos, q1 - 0.5),
                arrowprops=dict(facecolor='blue', arrowstyle='->'), ha='center')
    ax.annotate(f'Median: {median:.2f}', xy=(pos, median), xytext=(pos, median + 0.5),
                arrowprops=dict(facecolor='black', arrowstyle='->'), ha='center')
    ax.annotate(f'Q3: {q3:.2f}', xy=(pos, q3), xytext=(pos, q3 + 0.5),
                arrowprops=dict(facecolor='green', arrowstyle='->'), ha='center')
    ax.annotate(f'Max: {max_val:.2f}', xy=(pos, max_val), xytext=(pos, max_val + 0.5),
                arrowprops=dict(facecolor='red', arrowstyle='->'), ha='center')

plt.show()


# Calculate the correlation matrix
correlation_matrix = df.corr()

# Find pairs of columns with correlation coefficient greater than 0.45
high_correlation_pairs = []
threshold = 0.45
for i in range(len(correlation_matrix.columns)):
    for j in range(i+1, len(correlation_matrix.columns)):
        if abs(correlation_matrix.iloc[i, j]) > threshold:
            high_correlation_pairs.append((correlation_matrix.columns[i], correlation_matrix.columns[j]))

# Plot scatter plots for each pair with high correlation
for pair in high_correlation_pairs:
    plt.figure(figsize=(10, 6))
    sns.scatterplot(x=pair[0], y=pair[1], data=df)
    plt.title(f'Scatter Plot of {pair[0]} vs {pair[1]}\nCorrelation Coefficient: {correlation_matrix.loc[pair[0], pair[1]]:.2f}')
    plt.xlabel(pair[0])
    plt.ylabel(pair[1])
    plt.grid(True)
    plt.show()

    print(f'Scatter plot for {pair[0]} vs {pair[1]} (Correlation Coefficient: {correlation_matrix.loc[pair[0], pair[1]]:.2f})')

Scatter plot for Solubility vs MolLogP (Correlation Coefficient: -0.61)

Scatter plot for SD vs Ocurrences (Correlation Coefficient: 0.49)

Scatter plot for MolWt vs MolMR (Correlation Coefficient: 0.92)

Scatter plot for MolWt vs HeavyAtomCount (Correlation Coefficient: 0.95)

Scatter plot for MolWt vs NumHAcceptors (Correlation Coefficient: 0.73)

Scatter plot for MolWt vs NumHeteroatoms (Correlation Coefficient: 0.78)

Scatter plot for MolWt vs NumRotatableBonds (Correlation Coefficient: 0.61)

Scatter plot for MolWt vs NumValenceElectrons (Correlation Coefficient: 0.95)

Scatter plot for MolWt vs NumAromaticRings (Correlation Coefficient: 0.57)

Scatter plot for MolWt vs RingCount (Correlation Coefficient: 0.62)


# Correlation matrix
plt.figure(figsize=(20, 8))
sns.heatmap(df[numerical_cols].corr(), annot=True, fmt=".2f", cmap='coolwarm')
plt.show()


# Select numerical columns for PCA
numerical_cols = df.select_dtypes(include=[np.number]).columns
data = df[numerical_cols].dropna()

# Standardize the data
scaler = StandardScaler()
scaled_data = scaler.fit_transform(data)

# Apply PCA
pca = PCA(n_components=2)
principal_components = pca.fit_transform(scaled_data)

# Create a DataFrame with the principal components
pca_df = pd.DataFrame(data=principal_components, columns=['PC1', 'PC2'])

# Plot the principal components
plt.figure(figsize=(10, 6))
plt.scatter(pca_df['PC1'], pca_df['PC2'], alpha=0.7)
plt.xlabel('Principal Component 1')
plt.ylabel('Principal Component 2')
plt.title('PCA of Dataset')
plt.grid(True)
plt.show()

# Print the explained variance ratio
print(f'Explained variance ratio: {pca.explained_variance_ratio_}')

Explained variance ratio: [0.46329573 0.13466843]


pca_df


# Select numerical columns for clustering
numerical_cols = df.select_dtypes(include=[np.number]).columns
data = df[numerical_cols].dropna()

# Standardize the data
scaler = StandardScaler()
scaled_data = scaler.fit_transform(data)

# Determine the number of clusters using the Elbow method
wcss = []
for i in range(1, 11):
    kmeans = KMeans(n_clusters=i, random_state=42)
    kmeans.fit(scaled_data)
    wcss.append(kmeans.inertia_)

# Plot the Elbow method
plt.figure(figsize=(10, 6))
plt.plot(range(1, 11), wcss, marker='o')
plt.title('Elbow Method')
plt.xlabel('Number of clusters')
plt.ylabel('WCSS')
plt.grid(True)
plt.show()

# Apply K-means clustering with the chosen number of clusters (e.g., 3)
n_clusters = 3
kmeans = KMeans(n_clusters=n_clusters, random_state=42)
cluster_labels = kmeans.fit_predict(scaled_data)

# Add the cluster labels to the original dataframe
df['Cluster'] = cluster_labels

# Apply PCA to reduce dimensions for visualization
pca = PCA(n_components=2)
principal_components = pca.fit_transform(scaled_data)
pca_df = pd.DataFrame(data=principal_components, columns=['PC1', 'PC2'])
pca_df['Cluster'] = cluster_labels

# Plot the clusters
plt.figure(figsize=(10, 6))
sns.scatterplot(x='PC1', y='PC2', hue='Cluster', data=pca_df, palette='viridis', alpha=0.7)
plt.title('K-means Clustering with 2 Principal Components')
plt.xlabel('Principal Component 1')
plt.ylabel('Principal Component 2')
plt.legend(title='Cluster')
plt.grid(True)
plt.show()


from sklearn.metrics import silhouette_score

# Calculate the silhouette score
sil_score = silhouette_score(scaled_data, cluster_labels)
print(f'Silhouette Score: {sil_score:.2f}')

Silhouette Score: 0.24


silhouette_scores = []

# Try different numbers of clusters
for k in range(2, 11):
    kmeans = KMeans(n_clusters=k, random_state=42)
    cluster_labels = kmeans.fit_predict(scaled_data)
    sil_score = silhouette_score(scaled_data, cluster_labels)
    silhouette_scores.append((k, sil_score))

# Find the best number of clusters
best_k = max(silhouette_scores, key=lambda x: x[1])[0]
print(f'Best number of clusters: {best_k}')

# Plot silhouette scores
ks, scores = zip(*silhouette_scores)
plt.figure(figsize=(10, 6))
plt.plot(ks, scores, marker='o')
plt.title('Silhouette Scores for Different Numbers of Clusters')
plt.xlabel('Number of Clusters')
plt.ylabel('Silhouette Score')
plt.grid(True)
plt.show()

Best number of clusters: 2


# Select numerical columns for clustering
numerical_cols = df.select_dtypes(include=[np.number]).columns
data = df[numerical_cols].dropna()

# Standardize the data
scaler = StandardScaler()
scaled_data = scaler.fit_transform(data)

# Apply K-means clustering with the chosen number of clusters (2)
n_clusters = 2
kmeans = KMeans(n_clusters=n_clusters, random_state=42)
cluster_labels = kmeans.fit_predict(scaled_data)

# Add the cluster labels to the original dataframe
df['Cluster'] = cluster_labels

# Apply PCA to reduce dimensions for visualization
pca = PCA(n_components=2)
principal_components = pca.fit_transform(scaled_data)
pca_df = pd.DataFrame(data=principal_components, columns=['PC1', 'PC2'])
pca_df['Cluster'] = cluster_labels

# Plot the clusters
plt.figure(figsize=(10, 6))
sns.scatterplot(x='PC1', y='PC2', hue='Cluster', data=pca_df, palette='viridis', alpha=0.7)
plt.title('K-means Clustering with 2 Principal Components')
plt.xlabel('Principal Component 1')
plt.ylabel('Principal Component 2')
plt.legend(title='Cluster')
plt.grid(True)
plt.show()

# Calculate and print the silhouette score
from sklearn.metrics import silhouette_score
sil_score = silhouette_score(scaled_data, cluster_labels)
print(f'Silhouette Score with 2 clusters: {sil_score:.2f}')

Silhouette Score with 2 clusters: 0.58


# Add the cluster labels to the original dataframe
df['Cluster'] = cluster_labels

# Calculate mean and standard deviation of each feature within each cluster
cluster_profile = df.groupby('Cluster').agg(['mean', 'std'])
print(cluster_profile)

# Plot distributions of key features for each cluster
key_features = list(numerical_cols)
for feature in key_features:
    plt.figure(figsize=(10, 6))
    sns.histplot(data=df, x=feature, hue='Cluster', kde=True, element='step')
    plt.title(f'Distribution of {feature} by Cluster')
    plt.xlabel(feature)
    plt.ylabel('Frequency')
    plt.grid(True)
    plt.show()

C:\Users\PC\AppData\Local\Temp\ipykernel_20600\2471440816.py:5: FutureWarning: ['ID', 'Name', 'InChI', 'InChIKey', 'SMILES', 'Group'] did not aggregate successfully. If any error is raised this will raise in a future version of pandas. Drop these columns/ops to avoid this warning.
  cluster_profile = df.groupby('Cluster').agg(['mean', 'std'])

        Solubility                  SD           Ocurrences            \
              mean       std      mean       std       mean       std   
Cluster                                                                 
0        -2.812590  2.310309  0.067663  0.233803   1.389298  1.038462   
1        -4.059434  2.873393  0.064203  0.248083   1.208401  0.741856   

              MolWt               MolLogP            ... RingCount            \
               mean         std      mean       std  ...      mean       std   
Cluster                                              ...                       
0        234.638873  102.527906  1.912118  2.739906  ...  1.318167  1.235001   
1        751.107756  371.492830  2.993354  9.221262  ...  4.507270  3.317775   

               TPSA               LabuteASA              BalabanJ            \
               mean         std        mean         std      mean       std   
Cluster                                                                       
0         53.358059   40.312605   95.191858   40.325074  2.484675  1.019385   
1        200.113489  141.277100  316.452448  154.260009  0.993415  1.181835   

             BertzCT               
                mean          std  
Cluster                            
0         376.921924   276.188422  
1        1834.952790  1293.466717  

[2 rows x 40 columns]


# Descriptive statistics
cluster_descriptive_stats = df.groupby('Cluster').agg(['mean', 'median', 'std', 'min', 'max'])
print(cluster_descriptive_stats)

        Solubility                                                 SD         \
              mean    median       std        min       max      mean median   
Cluster                                                                        
0        -2.812590 -2.573579  2.310309 -13.171900  2.137682  0.067663    0.0   
1        -4.059434 -3.931000  2.873393 -11.998938  0.316973  0.064203    0.0   

                                  ...  BalabanJ                                \
              std  min       max  ...      mean    median       std       min   
Cluster                           ...                                           
0        0.233803  0.0  3.870145  ...  2.484675  2.595083  1.019385 -0.000004   
1        0.248083  0.0  2.191675  ...  0.993415  1.022751  1.181835 -0.000004   

                       BertzCT                                       \
              max         mean       median          std        min   
Cluster                                                               
0        7.517310   376.921924   325.349050   276.188422   0.000000   
1        7.372991  1834.952790  1552.141814  1293.466717  36.269827   

                       
                  max  
Cluster                
0         1517.612204  
1        20720.267708  

[2 rows x 100 columns]

C:\Users\PC\AppData\Local\Temp\ipykernel_20600\3970974338.py:2: FutureWarning: ['ID', 'Name', 'InChI', 'InChIKey', 'SMILES', 'Group'] did not aggregate successfully. If any error is raised this will raise in a future version of pandas. Drop these columns/ops to avoid this warning.
  cluster_descriptive_stats = df.groupby('Cluster').agg(['mean', 'median', 'std', 'min', 'max'])


from scipy.stats import ttest_ind

# Perform t-tests for each feature
features = numerical_cols
t_test_results = {}
for feature in features:
    cluster0_data = df[df['Cluster'] == 0][feature]
    cluster1_data = df[df['Cluster'] == 1][feature]
    t_stat, p_value = ttest_ind(cluster0_data, cluster1_data, equal_var=False)
    t_test_results[feature] = (t_stat, p_value)

# Display t-test results
for feature, (t_stat, p_value) in t_test_results.items():
    print(f"{feature}: t-statistic = {t_stat:.2f}, p-value = {p_value:.4f}")

Solubility: t-statistic = 10.57, p-value = 0.0000
SD: t-statistic = 0.34, p-value = 0.7360
Ocurrences: t-statistic = 5.71, p-value = 0.0000
MolWt: t-statistic = -34.50, p-value = 0.0000
MolLogP: t-statistic = -2.91, p-value = 0.0038
MolMR: t-statistic = -32.93, p-value = 0.0000
HeavyAtomCount: t-statistic = -35.77, p-value = 0.0000
NumHAcceptors: t-statistic = -26.52, p-value = 0.0000
NumHDonors: t-statistic = -16.55, p-value = 0.0000
NumHeteroatoms: t-statistic = -25.50, p-value = 0.0000
NumRotatableBonds: t-statistic = -17.97, p-value = 0.0000
NumValenceElectrons: t-statistic = -34.57, p-value = 0.0000
NumAromaticRings: t-statistic = -20.21, p-value = 0.0000
NumSaturatedRings: t-statistic = -4.54, p-value = 0.0000
NumAliphaticRings: t-statistic = -9.12, p-value = 0.0000
RingCount: t-statistic = -23.81, p-value = 0.0000
TPSA: t-statistic = -25.78, p-value = 0.0000
LabuteASA: t-statistic = -35.61, p-value = 0.0000
BalabanJ: t-statistic = 30.65, p-value = 0.0000
BertzCT: t-statistic = -28.00, p-value = 0.0000
Cluster: t-statistic = -inf, p-value = 0.0000

C:\Users\PC\AppData\Local\Temp\ipykernel_20600\4100536841.py:9: RuntimeWarning: Precision loss occurred in moment calculation due to catastrophic cancellation. This occurs when the data are nearly identical. Results may be unreliable.
  t_stat, p_value = ttest_ind(cluster0_data, cluster1_data, equal_var=False)


# Correlation matrices for each cluster
corr_cluster0 = df[df['Cluster'] == 0][numerical_cols].corr()
corr_cluster1 = df[df['Cluster'] == 1][numerical_cols].corr()

# Plot correlation matrices
import seaborn as sns
plt.figure(figsize=(20, 10))
sns.heatmap(corr_cluster0, annot=True, cmap='coolwarm')
plt.title('Correlation Matrix for Cluster 0')
plt.show()

plt.figure(figsize=(20, 10))
sns.heatmap(corr_cluster1, annot=True, cmap='coolwarm')
plt.title('Correlation Matrix for Cluster 1')
plt.show()


features = df.drop(columns=['Solubility', 'Cluster'])  # Exclude target and cluster label
target = df['Solubility']

# Split the data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(features, target, test_size=0.3, random_state=42)


# Check for non-numeric columns
non_numeric_cols = df.select_dtypes(exclude=[np.number]).columns
print("Non-numeric columns:", non_numeric_cols)

Non-numeric columns: Index(['ID', 'Name', 'InChI', 'InChIKey', 'SMILES', 'Group'], dtype='object')


from sklearn.preprocessing import OneHotEncoder

# One-hot encode non-numeric columns
df = pd.get_dummies(df, columns=non_numeric_cols, drop_first=True)


# Select features and target
features = df.drop(columns=['Solubility', 'Cluster'])  # Exclude target and cluster label
target = df['Solubility']

# Split the data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(features, target, test_size=0.2, random_state=42)

# Initialize the models
models = {
    'Linear Regression': LinearRegression(),
    'Decision Tree': DecisionTreeRegressor(random_state=42),
    'Random Forest': RandomForestRegressor(random_state=42)
}

# Train and evaluate each model
results = {}
for model_name, model in models.items():
    model.fit(X_train, y_train)
    y_pred = model.predict(X_test)
    
    # Calculate metrics
    mse = mean_squared_error(y_test, y_pred)
    rmse = mean_squared_error(y_test, y_pred, squared=False)
    r2 = r2_score(y_test, y_pred)
    mae = mean_absolute_error(y_test, y_pred)
    
    results[model_name] = {'MSE': mse, 'RMSE': rmse, 'R-squared': r2, 'MAE': mae}


# Display the results
results_df = pd.DataFrame(results).T
print(results_df)

                        MSE      RMSE  R-squared       MAE
Linear Regression  2.715572  1.647899   0.499401  1.205257
Decision Tree      2.043242  1.429420   0.623341  0.959217
Random Forest      1.226417  1.107437   0.773918  0.756546

	ID	Name	InChI	InChIKey	SMILES	Solubility	SD	Ocurrences	Group	MolWt	...	NumRotatableBonds	NumValenceElectrons	NumAromaticRings	NumSaturatedRings	NumAliphaticRings	RingCount	TPSA	LabuteASA	BalabanJ	BertzCT
0	A-3	N,N,N-trimethyloctadecan-1-aminium bromide	InChI=1S/C21H46N.BrH/c1-5-6-7-8-9-10-11-12-13-...	SZEMGTQCPRNXEG-UHFFFAOYSA-M	[Br-].CCCCCCCCCCCCCCCCCC[N+](C)(C)C	-3.616127	0.000000	1	G1	392.510	...	17.0	142.0	0.0	0.0	0.0	0.0	0.00	158.520601	0.000000e+00	210.377334
1	A-4	Benzo[cd]indol-2(1H)-one	InChI=1S/C11H7NO/c13-11-8-5-1-3-7-4-2-6-9(12-1...	GPYLCFQEKPUWLD-UHFFFAOYSA-N	O=C1Nc2cccc3cccc1c23	-3.254767	0.000000	1	G1	169.183	...	0.0	62.0	2.0	0.0	1.0	3.0	29.10	75.183563	2.582996e+00	511.229248
2	A-5	4-chlorobenzaldehyde	InChI=1S/C7H5ClO/c8-7-3-1-6(5-9)2-4-7/h1-5H	AVPYQKSLYISFPO-UHFFFAOYSA-N	Clc1ccc(C=O)cc1	-2.177078	0.000000	1	G1	140.569	...	1.0	46.0	1.0	0.0	0.0	1.0	17.07	58.261134	3.009782e+00	202.661065
3	A-8	zinc bis[2-hydroxy-3,5-bis(1-phenylethyl)benzo...	InChI=1S/2C23H22O3.Zn/c2*1-15(17-9-5-3-6-10-17...	XTUPUYCJWKHGSW-UHFFFAOYSA-L	[Zn++].CC(c1ccccc1)c2cc(C(C)c3ccccc3)c(O)c(c2)...	-3.924409	0.000000	1	G1	756.226	...	10.0	264.0	6.0	0.0	0.0	6.0	120.72	323.755434	2.322963e-07	1964.648666
4	A-9	4-({4-[bis(oxiran-2-ylmethyl)amino]phenyl}meth...	InChI=1S/C25H30N2O4/c1-5-20(26(10-22-14-28-22)...	FAUAZXVRLVIARB-UHFFFAOYSA-N	C1OC1CN(CC2CO2)c3ccc(Cc4ccc(cc4)N(CC5CO5)CC6CO...	-4.662065	0.000000	1	G1	422.525	...	12.0	164.0	2.0	4.0	4.0	6.0	56.60	183.183268	1.084427e+00	769.899934
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
9977	I-84	tetracaine	InChI=1S/C15H24N2O2/c1-4-5-10-16-14-8-6-13(7-9...	GKCBAIGFKIBETG-UHFFFAOYSA-N	C(c1ccc(cc1)NCCCC)(=O)OCCN(C)C	-3.010000	0.000000	1	G1	264.369	...	8.0	106.0	1.0	0.0	0.0	1.0	41.57	115.300645	2.394548e+00	374.236893
9978	I-85	tetracycline	InChI=1S/C22H24N2O8/c1-21(31)8-5-4-6-11(25)12(...	OFVLGDICTFRJMM-WESIUVDSSA-N	OC1=C(C(C2=C(O)[C@@](C(C(C(N)=O)=C(O)[C@H]3N(C...	-2.930000	0.000000	1	G1	444.440	...	2.0	170.0	1.0	0.0	3.0	4.0	181.62	182.429237	2.047922e+00	1148.584975
9979	I-86	thymol	InChI=1S/C10H14O/c1-7(2)9-5-4-8(3)6-10(9)11/h4...	MGSRCZKZVOBKFT-UHFFFAOYSA-N	c1(cc(ccc1C(C)C)C)O	-2.190000	0.019222	3	G5	150.221	...	1.0	60.0	1.0	0.0	0.0	1.0	20.23	67.685405	3.092720e+00	251.049732
9980	I-93	verapamil	InChI=1S/C27H38N2O4/c1-20(2)27(19-28,22-10-12-...	SGTNSNPWRIOYBX-UHFFFAOYSA-N	COc1ccc(CCN(C)CCCC(C#N)(C(C)C)c2ccc(OC)c(OC)c2...	-3.980000	0.000000	1	G1	454.611	...	13.0	180.0	2.0	0.0	0.0	2.0	63.95	198.569223	2.023333e+00	938.203977
9981	I-94	warfarin	InChI=1S/C19H16O4/c1-12(20)11-15(13-7-3-2-4-8-...	PJVWKTKQMONHTI-UHFFFAOYSA-N	CC(=O)CC(c1ccccc1)c1c(O)c2ccccc2oc1=O	-4.780000	0.450506	3	G5	308.333	...	4.0	116.0	3.0	0.0	0.0	3.0	67.51	132.552025	2.258072e+00	909.550973

	Solubility	SD	Ocurrences	MolWt	MolLogP	MolMR	HeavyAtomCount	NumHAcceptors	NumHDonors	NumHeteroatoms	NumRotatableBonds	NumValenceElectrons	NumAromaticRings	NumSaturatedRings	NumAliphaticRings	RingCount	TPSA	LabuteASA	BalabanJ	BertzCT
count	9982.000000	9982.000000	9982.000000	9982.000000	9982.000000	9982.000000	9982.000000	9982.000000	9982.000000	9982.000000	9982.000000	9982.000000	9982.000000	9982.000000	9982.000000	9982.000000	9982.000000	9982.000000	9982.000000	9982.000000
mean	-2.889909	0.067449	1.378081	266.665946	1.979167	66.794594	17.374674	3.486776	1.108595	5.196955	4.073031	94.243438	1.068323	0.292627	0.447606	1.515929	62.458601	108.912586	2.392199	467.336782
std	2.368154	0.234702	1.023476	184.179024	3.517738	46.523021	12.241536	3.498203	1.488973	4.736275	5.646925	64.748563	1.309427	0.879599	1.054667	1.644334	63.348307	76.462726	1.091123	546.631696
min	-13.171900	0.000000	1.000000	9.012000	-40.873200	0.000000	1.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	7.504228	-0.000004	0.000000
25%	-4.326325	0.000000	1.000000	162.276000	0.619750	40.602475	11.000000	2.000000	0.000000	3.000000	1.000000	58.000000	0.000000	0.000000	0.000000	0.000000	26.300000	66.623721	2.004357	163.243343
50%	-2.618173	0.000000	1.000000	228.682000	1.949220	58.633400	15.000000	3.000000	1.000000	4.000000	3.000000	82.000000	1.000000	0.000000	0.000000	1.000000	50.720000	93.299873	2.539539	351.640433
75%	-1.209735	0.000000	1.000000	320.436000	3.419030	81.938000	21.000000	4.000000	2.000000	6.000000	5.000000	112.000000	2.000000	0.000000	1.000000	2.000000	80.390000	129.118374	3.032456	606.562848
max	2.137682	3.870145	38.000000	5299.456000	68.541140	1419.351700	388.000000	86.000000	26.000000	89.000000	141.000000	2012.000000	35.000000	30.000000	30.000000	36.000000	1214.340000	2230.685124	7.517310	20720.267708

	ID	Name	InChI	InChIKey	SMILES	Solubility	SD	Ocurrences	Group	MolWt	...	NumRotatableBonds	NumValenceElectrons	NumAromaticRings	NumSaturatedRings	NumAliphaticRings	RingCount	TPSA	LabuteASA	BalabanJ	BertzCT
30	A-45	hydroxylamine	InChI=1S/H3NO/c1-2/h2H,1H2	AVXURJPOCDRRFD-UHFFFAOYSA-N	NO	-0.763034	0.861298	7	G4	33.030	...	0.0	14.0	0.0	0.0	0.0	0.0	46.25	12.462472	1.000000e+00	2.000000
87	A-142	1-methyl-4-(prop-1-en-2-yl)cyclohex-1-ene	InChI=1S/C10H16/c1-8(2)10-6-4-9(3)5-7-10/h4,10...	XMGQYMWWDOXHJM-UHFFFAOYSA-N	CC(=C)C1CCC(=CC1)C	-3.846497	0.730589	9	G4	136.238	...	1.0	56.0	0.0	0.0	1.0	1.0	0.00	63.638693	2.495412e+00	162.877124
151	A-254	calcium dihydroxide	InChI=1S/Ca.2H2O/h;2*1H2/q+2;;/p-2	AXCZMVOFGPJBDE-UHFFFAOYSA-L	[OH-].[OH-].[Ca++]	-1.910730	0.672750	7	G4	74.092	...	0.0	16.0	0.0	0.0	0.0	0.0	60.00	48.445753	-0.000000e+00	2.754888
226	A-382	triethylamine	InChI=1S/C6H15N/c1-4-7(5-2)6-3/h4-6H2,1-3H3	ZMANZCXQSJIPKH-UHFFFAOYSA-N	CCN(CC)CC	-0.137683	0.335493	7	G5	101.193	...	3.0	44.0	0.0	0.0	0.0	0.0	3.24	46.323795	2.992303e+00	25.651484
238	A-400	Hydrocarbons, C5-rich	InChI=1S/C5H12/c1-3-5-4-2/h3-5H2,1-2H3	OFBQJSOFQDEBGM-UHFFFAOYSA-N	CCCCC	-3.006984	0.421426	8	G5	72.151	...	2.0	32.0	0.0	0.0	0.0	0.0	0.00	34.199019	2.190610e+00	7.509775
292	A-491	benzene-1,2-dicarboxylic acid	InChI=1S/C8H6O4/c9-7(10)5-3-1-2-4-6(5)8(11)12/...	XNGIFLGASWRNHJ-UHFFFAOYSA-N	OC(=O)c1ccccc1C(O)=O	-1.424573	0.329865	8	G5	166.132	...	2.0	62.0	1.0	0.0	0.0	1.0	74.60	68.072799	3.267076e+00	296.584675
459	A-808	5-methyl-2-(propan-2-yl)cyclohexan-1-ol	InChI=1S/C10H20O/c1-7(2)9-5-4-8(3)6-10(9)11/h7...	NOOLISFMXDJSKH-KXUCPTDWSA-N	CC(C)[C@@H]1CC[C@@H](C)C[C@H]1O	-2.570624	0.045118	7	G5	156.269	...	1.0	66.0	0.0	1.0	1.0	1.0	20.23	69.812133	2.437159e+00	120.041185
534	A-954	1,2,4-trichlorobenzene	InChI=1S/C6H3Cl3/c7-4-1-2-5(8)6(9)3-4/h1-3H	PBKONEOXTCPAFI-UHFFFAOYSA-N	Clc1ccc(Cl)c(Cl)c1	-3.702452	0.124042	8	G5	181.449	...	0.0	48.0	1.0	0.0	0.0	1.0	0.00	68.341202	3.171678e+00	219.543000
665	A-1156	ethenylbenzene	InChI=1S/C8H8/c1-2-8-6-4-3-5-7-8/h2-7H,1H2	PPBRXRYQALVLMV-UHFFFAOYSA-N	C=Cc1ccccc1	-2.555270	0.104808	7	G5	104.152	...	1.0	40.0	1.0	0.0	0.0	1.0	0.00	49.471684	2.991047e+00	162.653001
751	A-1308	butylbenzene	InChI=1S/C10H14/c1-3-9(2)10-7-5-4-6-8-10/h4-9H...	ZJMWRROPUADPEA-UHFFFAOYSA-N	CCC(C)c1ccccc1	-3.758608	0.264324	7	G5	134.222	...	2.0	54.0	1.0	0.0	0.0	1.0	0.00	62.891172	2.746978e+00	176.489615
814	A-1414	oxostibanyl stibinate	InChI=1S/3O.2Sb/q3-2;2+3	GHPGOEFPKIHBNM-UHFFFAOYSA-N	[O--].[O--].[O--].[Sb+3].[Sb+3]	-5.023755	0.653110	10	G4	291.517	...	0.0	28.0	0.0	0.0	0.0	0.0	85.50	64.951844	-0.000000e+00	4.854753
835	A-1450	calcium bis(12-hydroxyoctadecanoate)	InChI=1S/2C18H36O3.Ca/c2*1-2-3-4-11-14-17(19)1...	RXPKHKBYUIHIGL-UHFFFAOYSA-L	[Ca++].CCCCCCC(O)CCCCCCCCCCC([O-])=O.CCCCCCC(O...	-5.463097	1.000831	13	G4	639.028	...	32.0	252.0	0.0	0.0	0.0	0.0	120.72	296.133803	-7.272727e-07	511.858709
918	A-1579	2,3-dihydro-1,2-benzothiazol-3-one	InChI=1S/C7H5NOS/c9-7-5-3-1-2-4-6(5)10-8-7/h1-...	DMSMPAJRVJJAGA-UHFFFAOYSA-N	O=C1NSc2ccccc12	-1.947290	0.235013	12	G5	151.190	...	0.0	50.0	2.0	0.0	0.0	2.0	32.86	61.275691	3.070615e+00	400.898353
967	A-1679	1,3-diphenylguanidine	InChI=1S/C13H13N3/c14-13(15-11-7-3-1-4-8-11)16...	OWRCNXZUPFZXOS-UHFFFAOYSA-N	NC(Nc1ccccc1)=Nc2ccccc2	-2.157516	1.067788	8	G4	211.268	...	2.0	80.0	2.0	0.0	0.0	2.0	50.41	94.638515	2.090928e+00	463.051084
1180	A-2032	2,6-dibromo-4-[2-(3,5-dibromo-4-hydroxyphenyl)...	InChI=1S/C15H12Br4O2/c1-15(2,7-3-9(16)13(20)10...	VEORPZCZECFIRK-UHFFFAOYSA-N	CC(C)(c1cc(Br)c(O)c(Br)c1)c2cc(Br)c(O)c(Br)c2	-5.694106	0.635897	7	G4	543.875	...	2.0	112.0	2.0	0.0	0.0	2.0	40.46	156.641982	2.614907e+00	605.305185
1241	A-2147	tetradecan-1-ol	InChI=1S/C14H30O/c1-2-3-4-5-6-7-8-9-10-11-12-1...	HLZKNKRTKFSKGZ-UHFFFAOYSA-N	CCCCCCCCCCCCCCO	-5.787143	0.301618	7	G5	214.393	...	12.0	92.0	0.0	0.0	0.0	0.0	20.23	96.277732	2.807926e+00	89.511823
1300	A-2257	1,2-bis(2-ethylhexyl) benzene-1,2-dicarboxylate	InChI=1S/C24H38O4/c1-5-9-13-19(7-3)17-27-23(25...	BJQHLKABXJIVAM-UHFFFAOYSA-N	CCCCC(CC)COC(=O)c1ccccc1C(=O)OCC(CC)CCCC	-6.978908	0.613829	7	G4	390.564	...	14.0	158.0	1.0	0.0	0.0	1.0	52.60	170.550496	2.690590e+00	530.722810
1368	A-2377	4,7,7-trimethylbicyclo[3.1.1]hept-3-ene	InChI=1S/C10H16/c1-7-4-5-8-6-9(7)10(8,2)3/h4,8...	GRWFGVWFFZKLTI-UHFFFAOYSA-N	CC1=CCC2CC1C2(C)C	-3.772570	0.698272	10	G4	136.238	...	0.0	56.0	0.0	1.0	3.0	3.0	0.00	63.322465	2.296627e+00	186.214991
1857	A-3047	1,2-dichlorobenzene	InChI=1S/C6H4Cl2/c7-5-3-1-2-4-6(5)8/h1-4H	RFFLAFLAYFXFSW-UHFFFAOYSA-N	Clc1ccccc1Cl	-3.053386	0.079736	8	G5	147.004	...	0.0	42.0	1.0	0.0	0.0	1.0	0.00	58.037936	3.134862e+00	162.638339
1983	A-3266	sodium formate	InChI=1S/CH2O2.Na/c2-1-3;/h1H,(H,2,3);/q;+1/p-1	HLBBKKJFGFRGMU-UHFFFAOYSA-M	[Na+].[O-]C=O	1.012544	0.128539	7	G5	68.007	...	0.0	18.0	0.0	0.0	0.0	0.0	40.13	46.108407	0.000000e+00	13.509775
1985	A-3273	acid D,L-aspart	InChI=1S/C4H7NO4/c5-2(4(8)9)1-3(6)7/h2H,1,5H2,...	CKLJMWTZIZZHCS-UHFFFAOYSA-N	NC(CC(O)=O)C(O)=O	-1.229318	0.359384	8	G5	133.103	...	3.0	52.0	0.0	0.0	0.0	0.0	100.62	51.085480	3.632432e+00	132.529325
2017	A-3330	iron(3+) chloride sulfate	InChI=1S/Cl.Fe.H2O4S/c;;1-5(2,3)4/h;;(H2,1,2,3...	NGYBMUURDZXEEA-UHFFFAOYSA-L	[Cl].[Fe].[O-][S]([O-])(=O)=O	0.540234	0.378887	8	G5	187.361	...	0.0	47.0	0.0	0.0	0.0	0.0	80.26	57.754896	-8.000000e-08	94.858202
2018	A-3331	iron(3+) ion trichloride	InChI=1S/3ClH.Fe/h3*1H;/q;;;+3/p-3	RBTARNINKXHZNM-UHFFFAOYSA-K	[Cl-].[Cl-].[Cl-].[Fe+3]	0.602852	0.378887	8	G5	162.204	...	0.0	29.0	0.0	0.0	0.0	0.0	0.00	54.423378	-0.000000e+00	3.245112
2019	A-3333	iron(+2) cation sulfate	InChI=1S/Fe.H2O4S/c;1-5(2,3)4/h;(H2,1,2,3,4)/q...	BAUYGSIQEAFULO-UHFFFAOYSA-L	[Fe++].[O-][S]([O-])(=O)=O	0.631333	0.378887	8	G5	151.908	...	0.0	38.0	0.0	0.0	0.0	0.0	80.26	45.601803	0.000000e+00	90.716493
2089	A-3446	(2R,3R)-2,3-dihydroxybutanedioic acid	InChI=1S/C4H6O6/c5-1(3(7)8)2(6)4(9)10/h1-2,5-6...	FEWJPZIEWOKRBE-UHFFFAOYSA-N	OC(C(O)C(O)=O)C(O)=O	0.571848	0.682833	10	G4	150.086	...	3.0	58.0	0.0	0.0	0.0	0.0	115.06	55.334057	4.069512e+00	133.826806
2091	A-3448	potassium hydrogen tartarate	InChI=1S/C4H6O6.K/c5-1(3(7)8)2(6)4(9)10;/h1-2,...	KYKNRZGSIGMXFH-ZVGUSBNCSA-M	[K+].O[C@H]([C@@H](O)C([O-])=O)C(O)=O	0.473624	0.753304	8	G4	188.176	...	3.0	58.0	0.0	0.0	0.0	0.0	117.89	104.256621	0.000000e+00	138.661273
2733	A-4559	3-bromo-1-(3-chloropyridin-2-yl)-1H-pyrazole-5...	InChI=1S/C9H5BrClN3O2/c10-7-4-6(9(15)16)14(13-...	FORBXGROTPOMEH-UHFFFAOYSA-N	OC(=O)c1cc(Br)nn1c2ncccc2Cl	-1.448935	1.502581	7	G4	302.515	...	2.0	82.0	2.0	0.0	0.0	2.0	68.01	103.806891	2.643285e+00	555.437168
2887	A-4830	chlorobenzene	InChI=1S/C6H5Cl/c7-6-4-2-1-3-5-6/h1-5H	MVPPADPHJFYWMZ-UHFFFAOYSA-N	Clc1ccccc1	-2.449320	0.132559	8	G5	112.559	...	0.0	36.0	1.0	0.0	0.0	1.0	0.00	47.734669	3.021465e+00	134.107370
3002	A-5028	methyl 2-[(4-ethoxy-6-methylamino-1,3,5-triazi...	InChI=1S/C15H18N6O6S/c1-4-27-15-19-12(16-2)17-...	ZINJLDJMHCUBIP-UHFFFAOYSA-N	CCOc1nc(NC)nc(NC(=O)N[S](=O)(=O)c2ccccc2C(=O)O...	-4.387911	1.388382	8	G4	410.412	...	7.0	150.0	2.0	0.0	0.0	2.0	161.50	160.297591	2.235189e+00	980.736675
3387	A-5577	dioxotungsten	InChI=1S/2O.W	DZKDPOPGYFUOGI-UHFFFAOYSA-N	O=[W]=O	-5.955730	0.637644	9	G4	215.838	...	0.0	18.0	0.0	0.0	0.0	0.0	34.14	25.984794	3.265986e+00	23.774438
3393	A-5587	cobalt sulphide	InChI=1S/Co.S/q+2;-2	INPLXZPZQSLHBR-UHFFFAOYSA-N	[S--].[Co++]	-5.015250	1.028126	27	G4	91.000	...	0.0	15.0	0.0	0.0	0.0	0.0	0.00	30.881366	0.000000e+00	2.000000
3394	A-5589	methane; vanadium	InChI=1S/CH4.V/h1H4;	GORXZVFEOLUTMI-UHFFFAOYSA-N	C.[V]	-6.205842	0.982342	8	G4	66.985	...	0.0	13.0	0.0	0.0	0.0	0.0	0.00	26.747394	0.000000e+00	2.000000
3427	A-5674	Aluminum;phosphenic acid	InChI=1S/Al.3H3O3P/c;31-4(2)3/h;34H,(H2,1,2,...	PGOXTIQAMARHNF-UHFFFAOYSA-K	[Al+3].O[PH]([O-])=O.O[PH]([O-])=O.O[PH]([O-])=O	-4.770881	1.247611	9	G4	269.943	...	0.0	78.0	0.0	0.0	0.0	0.0	181.08	85.659023	-4.500000e-08	112.409479
3431	A-5680	cobaltoylol	InChI=1S/Co.H2O.O/h;1H2;/q+1;;/p-1	DLHSXQSAISCVNN-UHFFFAOYSA-M	O[Co]=O	-6.275971	0.991201	16	G4	91.939	...	0.0	22.0	0.0	0.0	0.0	0.0	37.30	23.955846	2.187496e+00	10.264663
3433	A-5686	cobalt	InChI=1S/Co	GUTLYIVDDKVIGB-UHFFFAOYSA-N	[Co]	-5.117146	1.364118	38	G4	58.933	...	0.0	9.0	0.0	0.0	0.0	0.0	0.00	17.688511	0.000000e+00	0.000000
3451	A-5731	cobalt(2+) oxalate	InChI=1S/C2H2O4.Co/c3-1(4)2(5)6;/h(H,3,4)(H,5,...	MULYSYXKGICWJF-UHFFFAOYSA-L	[Co++].[O-]C(=O)C([O-])=O	-4.667788	0.754840	13	G4	146.951	...	0.0	41.0	0.0	0.0	0.0	0.0	80.26	49.335738	0.000000e+00	75.690584
3499	A-5838	Cobaltous carbonate	InChI=1S/CH2O3.Co/c2-1(3)4;/h(H2,2,3,4);/q;+2/p-2	ZOTKGJBKKKVBJZ-UHFFFAOYSA-L	[Co++].[O-]C([O-])=O	-4.837537	1.007624	16	G4	118.941	...	0.0	31.0	0.0	0.0	0.0	0.0	63.19	38.809274	0.000000e+00	29.874303
3508	A-5852	Cobaltous 2-ethylhexanoate	InChI=1S/2C8H16O2.Co/c2*1-3-5-6-7(4-2)8(9)10;/...	QAEKNCDIHIGLFI-UHFFFAOYSA-L	[Co++].CCCCC(CC)C([O-])=O.CCCCC(CC)C([O-])=O	-5.347978	1.946375	12	G4	345.345	...	10.0	127.0	0.0	0.0	0.0	0.0	80.26	139.450759	-2.945454e-07	230.661531
3523	A-5888	oxocobalt	InChI=1S/Co.O	IVMYJDGYRUAWML-UHFFFAOYSA-N	O=[Co]	-5.798391	1.313112	16	G4	74.932	...	0.0	15.0	0.0	0.0	0.0	0.0	17.07	20.447360	2.000000e+00	2.000000
3755	B-162	methane	InChI=1S/CH4/h1H4	VNWKTOKETHGBQD-UHFFFAOYSA-N	C	-2.862900	1.591275	13	G4	16.043	...	0.0	8.0	0.0	0.0	0.0	0.0	0.00	8.739251	0.000000e+00	0.000000
4230	B-900	potassium sodium tartrate	InChI=1S/C4H6O6.K.Na/c5-1(3(7)8)2(6)4(9)10;;/h...	LJCNRYVRMXRIQR-OLXYHTOASA-L	[Na+].[K+].O[C@H]([C@@H](O)C([O-])=O)C([O-])=O	0.398400	0.710847	9	G4	210.158	...	3.0	58.0	0.0	0.0	0.0	0.0	120.72	132.670021	-4.050000e-07	143.627075
9808	G-776	Lindane	InChI=1S/C6H6Cl6/c7-1-2(8)4(10)6(12)5(11)3(1)9...	JLYXXMFPNIAWKQ-UHFFFAOYSA-N	ClC1C(Cl)C(Cl)C(Cl)C(Cl)C1Cl	-4.640000	0.523626	8	G4	290.832	...	0.0	72.0	0.0	1.0	1.0	1.0	0.00	101.377728	2.760252e+00	103.587975

	PC1	PC2
0	0.427680	1.811586
1	-0.863636	0.471152
2	-2.213924	0.425315
3	7.877660	2.215719
4	3.949742	0.375230
...	...	...
9977	0.033225	0.504861
9978	4.156564	-2.543008
9979	-1.962507	0.533362
9980	2.968548	1.681064
9981	1.319624	1.291313

`Impact of Molecular Descriptors on Solubility Prediction in Chemical Compounds`¶

`Data Cleaning & Preprocessing`¶

`Descriptive Statistics & Univariate Analysis`¶

`Box Plots`¶

`Bivariate Analysis`¶

`Multivariate Analysis`¶

`Principal Component Analysis`¶

`Cluster Analysis`¶

`Statistical Analysis`¶

`Model Building`¶

`Conclusion`¶

References¶

Impact of Molecular Descriptors on Solubility Prediction in Chemical Compounds¶

Data Cleaning & Preprocessing¶

Descriptive Statistics & Univariate Analysis¶

Box Plots¶

Bivariate Analysis¶

Multivariate Analysis¶

Principal Component Analysis¶

Cluster Analysis¶

Statistical Analysis¶

Model Building¶

Conclusion¶

References¶

`Impact of Molecular Descriptors on Solubility Prediction in Chemical Compounds`¶

`Data Cleaning & Preprocessing`¶

`Descriptive Statistics & Univariate Analysis`¶

`Box Plots`¶

`Bivariate Analysis`¶

`Multivariate Analysis`¶

`Principal Component Analysis`¶

`Cluster Analysis`¶

`Statistical Analysis`¶

`Model Building`¶

`Conclusion`¶